© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29713
    Prev
    Next
    INDEX
    Explanations

    Google drive sync

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     диза
    0.46
    ਨ
    0.46
     бо
    0.45
    θν
    0.45
     أج
    0.45
    ారణ
    0.45
    మన్
    0.45
     противополо
    0.45
    tttt
    0.44
    }$;
    0.43
    POSITIVE LOGITS
    UMP
    0.45
    INA
    0.44
     to
    0.43
    ATIONS
    0.43
    MI
    0.43
    TRO
    0.42
    CG
    0.42
    CZ
    0.42
     তাদের
    0.41
    Ổ
    0.41
    Activations Density 0.000%

    No Known Activations